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

    Neuronpedia

    INDEX
    Explanations

    references to dolls

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rament
    -0.74
    ################
    -0.74
    ãĥ¥
    -0.74
    TAIN
    -0.71
    GGGGGGGG
    -0.71
    ELY
    -0.71
    utherford
    -0.69
    RAW
    -0.69
     TRANS
    -0.69
    acular
    -0.68
    POSITIVE LOGITS
    maker
    0.93
     doll
    0.90
     dolls
    0.89
    hops
    0.84
    imates
    0.82
    ongs
    0.77
    oru
    0.76
     Doll
    0.75
    wright
    0.75
    ophone
    0.73
    Act Density 1.108%

    No Known Activations