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

    Neuronpedia

    INDEX
    Explanations

    words related to natural disasters and their aftermath

    oai_token-act-pair · gpt-3.5-turbo

    the presence of various suffixes and endings commonly associated with specific word types or forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hacker
    -0.80
    çĶ°
    -0.69
     Crunch
    -0.68
     Unlimited
    -0.67
     Lightning
    -0.66
     Buk
    -0.64
     Carib
    -0.64
    ãģ®å®
    -0.63
     Dusk
    -0.62
    76561
    -0.62
    POSITIVE LOGITS
    ilk
    0.84
    urnal
    0.82
    ishly
    0.82
    ards
    0.81
    uable
    0.80
    selves
    0.79
    thens
    0.78
    arious
    0.78
    urities
    0.78
    rely
    0.77
    Act Density 0.146%

    No Known Activations