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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions based on a set identity or belief

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the concept of "name" as it relates to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rued
    -0.71
    sbm
    -0.71
    quished
    -0.70
    yrinth
    -0.67
    tumblr
    -0.65
    resent
    -0.65
    isexual
    -0.63
    redd
    -0.63
    EMS
    -0.62
    raped
    -0.62
    POSITIVE LOGITS
    paces
    0.75
     recognition
    0.73
     Allaah
    0.72
    akes
    0.69
    ames
    0.67
    plates
    0.66
    esis
    0.65
    lessness
    0.65
    ãģŁ
    0.65
    wash
    0.64
    Act Density 0.016%

    No Known Activations