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

    Neuronpedia

    INDEX
    Explanations

    references to full-time employment

    oai_token-act-pair · gpt-3.5-turbo

    references to full-time employment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.91
    acid
    -0.79
    ĸļ
    -0.76
     tomat
    -0.76
    amar
    -0.75
    ukong
    -0.69
    ggles
    -0.68
    aution
    -0.68
    iosyncr
    -0.68
    apesh
    -0.67
    POSITIVE LOGITS
     equivalents
    0.77
     continuum
    0.69
     Bucc
    0.69
    motion
    0.69
     employment
    0.68
    frames
    0.67
     basis
    0.66
     acting
    0.64
    visor
    0.63
    âĶĢâĶĢ
    0.61
    Act Density 0.022%

    No Known Activations