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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "inspired" and concepts related to creativity or motivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     against
    -0.53
     diệt
    -0.52
    anti
    -0.51
    jet
    -0.51
    どうなる
    -0.48
     düş
    -0.48
     škol
    -0.47
     Fiske
    -0.46
     anti
    -0.46
     prisonniers
    -0.46
    POSITIVE LOGITS
     nick
    0.82
     inspire
    0.82
     surla
    0.81
     inspirations
    0.80
    Hochspringen
    0.77
    apimachinery
    0.76
     Roskov
    0.76
     inspiration
    0.74
    .~(\
    0.73
    ">//
    0.72
    Act Density 0.141%

    No Known Activations