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

    Neuronpedia

    INDEX
    Explanations

    words related to tall buildings and medical devices (specifically stretchers)

    oai_token-act-pair · gpt-3.5-turbo

    words related to construction or physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neut
    -0.74
    İĭ
    -0.67
    otten
    -0.66
    uci
    -0.64
    Reviewer
    -0.64
    ENN
    -0.63
    ndra
    -0.62
    mos
    -0.60
    sch
    -0.59
    orians
    -0.58
    POSITIVE LOGITS
    oute
    0.77
     Adin
    0.71
    lihood
    0.70
    ishly
    0.66
    mania
    0.65
    Ø©
    0.65
     extraord
    0.62
     Hale
    0.62
    hire
    0.62
    ught
    0.60
    Act Density 0.192%

    No Known Activations