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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of putting an end to something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that call for the termination of practices or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    king
    -0.71
    æ©Ł
    -0.64
     Maker
    -0.63
    thouse
    -0.62
    Maker
    -0.61
    itsch
    -0.61
     refill
    -0.59
    rious
    -0.59
    £ı
    -0.59
    esome
    -0.58
    POSITIVE LOGITS
    angering
    1.24
    owment
    1.18
    ocrin
    0.91
    tackle
    0.89
    angers
    0.86
    angered
    0.84
    ocrine
    0.84
    orses
    0.80
    eared
    0.75
    ogenous
    0.73
    Act Density 0.047%

    No Known Activations