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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences discussing similarities or shared attributes between different entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote commonalities or shared traits among subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helicop
    -0.76
    erd
    -0.73
    onso
    -0.73
    otos
    -0.72
    icer
    -0.72
    ideshow
    -0.71
    oby
    -0.71
    lectic
    -0.70
    gur
    -0.70
    eki
    -0.69
    POSITIVE LOGITS
    alities
    0.93
    wealth
    0.93
    clusions
    0.79
     decency
    0.76
     amongst
    0.73
     among
    0.71
     distinguishing
    0.71
     resemblance
    0.70
     ancestry
    0.70
     between
    0.66
    Act Density 0.023%

    No Known Activations