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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific circumstances or requirements

    oai_token-act-pair · gpt-3.5-turbo

    references to various conditions, particularly in socio-political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.95
    umbn
    -0.79
    ilus
    -0.78
    ramid
    -0.76
    adesh
    -0.76
     Flavoring
    -0.70
    ritz
    -0.69
    ilee
    -0.68
    yright
    -0.68
    zac
    -0.66
    POSITIVE LOGITS
     conditions
    1.08
    pring
    0.91
     Conditions
    0.91
     conducive
    0.91
     deterior
    0.88
     deteriorated
    0.85
     worsened
    0.83
     quo
    0.82
     condition
    0.77
    aldehyde
    0.77
    Act Density 0.021%

    No Known Activations