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

    Neuronpedia

    INDEX
    Explanations

    words related to physical feelings or sensations, especially negative ones

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "fe" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worthy
    -0.73
     GEAR
    -0.69
    antically
    -0.67
     ANGEL
    -0.63
    stood
    -0.62
    stretched
    -0.62
    ova
    -0.61
    70710
    -0.61
     Colleges
    -0.60
     owl
    -0.59
    POSITIVE LOGITS
    eling
    1.09
    els
    0.98
    ck
    0.95
    ffer
    0.94
    lda
    0.93
    cking
    0.93
    cker
    0.91
    elin
    0.90
    efe
    0.89
    ruary
    0.88
    Act Density 0.006%

    No Known Activations