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

    Neuronpedia

    INDEX
    Explanations

    names of public figures and terms related to hacking and security

    oai_token-act-pair · gpt-3.5-turbo

    instances of notable individuals and events related to public controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âķIJâķIJ
    -0.52
     Supported
    -0.49
     Kinnikuman
    -0.49
     pestic
    -0.49
     Attribution
    -0.48
    VIDIA
    -0.48
     opio
    -0.47
     incorpor
    -0.46
    ItemThumbnailImage
    -0.45
    urgical
    -0.44
    POSITIVE LOGITS
     onto
    0.73
    gently
    0.64
    selves
    0.64
     goodbye
    0.63
     into
    0.61
    Downloadha
    0.58
    onto
    0.57
    izont
    0.54
     havoc
    0.54
    pes
    0.53
    Act Density 1.240%

    No Known Activations