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

    Neuronpedia

    INDEX
    Explanations

    adjectives indicating something is of high interest or attraction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fascinating" and related terms indicating interest or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.74
    appa
    -0.73
    gs
    -0.73
    annis
    -0.72
    eva
    -0.71
    ramid
    -0.71
    abad
    -0.71
    xus
    -0.68
    ppo
    -0.68
    idation
    -0.66
    POSITIVE LOGITS
    ly
    1.12
     fascinating
    0.81
    ously
    0.76
    ĸļ
    0.74
    ingly
    0.74
     tales
    0.74
     tale
    0.73
     discoveries
    0.72
    ulously
    0.71
     orbs
    0.71
    Act Density 0.029%

    No Known Activations