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

    Neuronpedia

    INDEX
    Explanations

    phrases related to doing the right thing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahon
    -0.74
    NetMessage
    -0.71
    CLUD
    -0.70
    TAIN
    -0.69
    ockey
    -0.69
    haps
    -0.65
    acked
    -0.65
    inav
    -0.65
    urat
    -0.64
    ERSON
    -0.63
    POSITIVE LOGITS
     financially
    0.86
     defensively
    0.82
    fulness
    0.82
     offensively
    0.79
     morally
    0.72
    .#
    0.71
     outweigh
    0.71
     ¯
    0.71
     sacrificing
    0.71
     anonymously
    0.71
    Act Density 0.028%

    No Known Activations