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

    Neuronpedia

    INDEX
    Explanations

    the word 'ended' typically used in a past tense construction

    oai_token-act-pair · gpt-4-turbo

    phrases related to events reaching a conclusion or ending

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ended" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ña
    -0.84
    esis
    -0.82
    arij
    -0.77
    issance
    -0.77
    alty
    -0.76
    htaking
    -0.76
    gae
    -0.73
    ascar
    -0.71
    otta
    -0.71
    Appearance
    -0.70
    POSITIVE LOGITS
    angering
    0.88
    owment
    0.84
     abruptly
    0.82
    ocrin
    0.78
     tragically
    0.77
     prematurely
    0.70
     ends
    0.69
     Turns
    0.68
    tackle
    0.67
    ocrine
    0.67
    Act Density 0.022%

    No Known Activations