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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical interaction or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.15
    aza
    -0.15
    NU
    -0.15
     boca
    -0.15
    вÑĸ
    -0.15
    atti
    -0.15
    ipel
    -0.15
    ariat
    -0.15
    .builders
    -0.15
    loat
    -0.15
    POSITIVE LOGITS
     away
    0.20
     harder
    0.20
     holes
    0.19
     hardest
    0.18
     hard
    0.18
    @nate
    0.17
     HARD
    0.16
     into
    0.16
     down
    0.16
     against
    0.15
    Act Density 0.092%

    No Known Activations