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

    Neuronpedia

    INDEX
    Explanations

    terms related to significant outcomes and consequences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imest
    -0.17
    stra
    -0.17
    okens
    -0.15
    uncate
    -0.14
    uetype
    -0.14
    olly
    -0.14
    icamente
    -0.14
    ÏĦιν
    -0.13
     Opinion
    -0.13
    147
    -0.13
    POSITIVE LOGITS
     emphasis
    0.24
     regard
    0.23
    stood
    0.23
    eld
    0.18
    standing
    0.18
     implications
    0.18
    lac
    0.18
     regards
    0.17
    emphasis
    0.17
     added
    0.16
    Act Density 0.228%

    No Known Activations