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

    Neuronpedia

    INDEX
    Explanations

    words related to magic

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Magic" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lishes
    -0.84
     Fas
    -0.70
    dated
    -0.68
    hovah
    -0.67
    heres
    -0.65
    romising
    -0.65
    gets
    -0.61
    anke
    -0.60
    eling
    -0.58
     stern
    -0.58
    POSITIVE LOGITS
    ussen
    0.86
     Leap
    0.85
    haus
    0.82
    ian
    0.82
    wagen
    0.78
    andise
    0.77
    matic
    0.76
     Beans
    0.75
     Missile
    0.73
    oline
    0.73
    Act Density 0.029%

    No Known Activations