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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating a movement or transition

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "into" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hop
    -0.70
    zai
    -0.68
    otaur
    -0.68
    wagen
    -0.64
    die
    -0.57
     insulted
    -0.56
     indeed
    -0.56
    æ©Ł
    -0.55
     fork
    -0.55
     paced
    -0.54
    POSITIVE LOGITS
     adulthood
    1.07
     infinity
    0.76
     existence
    0.69
    izoph
    0.68
     adolescence
    0.65
    Role
    0.65
    veyard
    0.65
    inner
    0.64
    ãĤ§
    0.64
    uild
    0.63
    Act Density 0.074%

    No Known Activations