Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to specific groups or practices such as idol worship, military service, Nobel Prize laureates, subscribers, adopters, and followers

    oai_token-act-pair · gpt-3.5-turbo

    concerns related to regulations and the sale of services or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pronoun
    -0.76
     prism
    -0.75
     indictment
    -0.72
     metaphor
    -0.72
     interchange
    -0.71
     suspension
    -0.69
     handshake
    -0.69
     sacrament
    -0.69
     Archdemon
    -0.67
     compound
    -0.67
    POSITIVE LOGITS
    erers
    1.62
    ateurs
    1.58
    ancers
    1.53
    itors
    1.52
    ists
    1.51
    blers
    1.50
    esters
    1.47
    arians
    1.46
    arers
    1.43
    iners
    1.43
    Act Density 0.293%

    No Known Activations