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

    Neuronpedia

    INDEX
    Explanations

    phrases related to building or creation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of building projects or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edi
    -0.77
    jee
    -0.73
    seek
    -0.73
    Ö¼
    -0.69
    ANCE
    -0.67
    otiation
    -0.66
    admin
    -0.63
    hyde
    -0.63
    zzle
    -0.63
    pport
    -0.62
    POSITIVE LOGITS
     fences
    0.74
     prototypes
    0.69
     semic
    0.69
     groundwork
    0.69
     infrastructure
    0.68
     footh
    0.67
     nests
    0.67
     arsen
    0.67
     Strongh
    0.67
     Fortress
    0.66
    Act Density 0.192%

    No Known Activations