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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships to different entities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    consul
    -0.62
    良かった
    -0.55
    underwater
    -0.54
     policiales
    -0.54
    astéro
    -0.54
    Consul
    -0.53
     CURIAM
    -0.52
    }")]
    -0.52
    よかった
    -0.51
     Boswell
    -0.50
    POSITIVE LOGITS
     Sixteenth
    0.57
    TEEN
    0.52
    teen
    0.50
     fifteen
    0.49
     fifteenth
    0.48
    teenth
    0.47
    UNRELATED
    0.47
     quinze
    0.47
    atorze
    0.46
     Fourteen
    0.45
    Act Density 0.506%

    No Known Activations