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

    Neuronpedia

    INDEX
    Explanations

    signs and symbols related to traffic and direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DropTable
    -0.79
     OMIT
    -0.71
    /*
    -0.69
    makeText
    -0.66
    帖最后由
    -0.65
     ***!
    -0.63
     ]
    -0.61
    ibilité
    -0.59
    zzar
    -0.58
    érations
    -0.58
    POSITIVE LOGITS
     mauvaises
    0.55
     présidenti
    0.52
     découver
    0.50
     estren
    0.50
    KEYCODE
    0.48
    lorum
    0.47
     appuntamento
    0.47
     demikian
    0.47
     originaux
    0.46
     suyo
    0.46
    Act Density 0.516%

    No Known Activations