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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direction or progression towards a goal or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /w
    -0.16
    ek
    -0.15
    imer
    -0.14
    ares
    -0.14
    ute
    -0.14
     IConfiguration
    -0.13
    arity
    -0.13
    ÅĻÃŃklad
    -0.13
    _NEAR
    -0.13
    losing
    -0.13
    POSITIVE LOGITS
    GGLE
    0.18
    ies
    0.17
     toward
    0.17
     Tow
    0.16
    /from
    0.16
     towards
    0.16
    ement
    0.16
    ships
    0.15
    esch
    0.15
    sWith
    0.14
    Act Density 0.027%

    No Known Activations