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

    Neuronpedia

    INDEX
    Explanations

    phrases related to abandonment or leaving situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appa
    -0.18
    daq
    -0.15
    ilo
    -0.15
     Tale
    -0.14
    egin
    -0.14
    320
    -0.14
    orrect
    -0.13
    åĻ¨
    -0.13
    atsu
    -0.13
     likeness
    -0.13
    POSITIVE LOGITS
    -handed
    0.18
    /GPL
    0.18
    vens
    0.17
    enschaft
    0.17
    омÑĸ
    0.16
    aside
    0.16
    -wing
    0.15
    afen
    0.15
    undef
    0.15
    woord
    0.15
    Act Density 0.081%

    No Known Activations