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

    Neuronpedia

    INDEX
    Explanations

    references to human beings and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAG
    -0.72
    eryl
    -0.71
    urations
    -0.69
    liga
    -0.68
    forth
    -0.68
    kick
    -0.67
    arella
    -0.66
    è¦
    -0.66
    chell
    -0.65
    REP
    -0.65
    POSITIVE LOGITS
     beings
    1.45
    oids
    1.16
    itarian
    1.11
    itar
    1.08
     readable
    1.00
     embryonic
    0.97
    istic
    0.93
    zee
    0.93
    oid
    0.91
     fra
    0.89
    Act Density 0.025%

    No Known Activations